.png){kind=icon}
返回
Multiform Ensemble Self-Supervised Learning for Few-Shot Remote Sensing Scene Classification
.png){kind=icon}
PRE
AI
DOI：10.1109/TGRS.2023.3234252.png)
.png){kind=icon}
原文求助.png){kind=icon}
分享.png){kind=icon}
收藏
摘要
En 中文
Self-supervised learning is an effective way to solve model collapse for few-shot remote sensing scene classification (FSRSSC). However, most self-supervised contrastive learning auxiliary tasks perform poorly on the high interclass similarity problem in FSRSSC. Furthermore, it is time-consuming and computationally expensive to obtain the best combination among numerous self-supervised auxiliary tasks. In practical applications, we may encounter difficulties in remote sensing data acquisition and labeling, while most FSRSSC studies only focus on the former. To alleviate the above problems, we propose a multiform ensemble self-supervised learning ((MESL)-L-2) framework for FSRSSC in this article. Based on the transfer learning-based few-shot scheme, we design a novel global-local contrastive learning auxiliary task to solve the low interclass separability problem. The self-attention mechanism is designed in the local contrast features to investigate the intrinsic associations between different remote sensing scene objectives. We also present a multiform ensemble enhancement (MEE) training method. Ensemble enhancement involves the concatenation of features extracted from different backbones trained by a combination of multiform self-supervised auxiliary tasks. MEE can not only be regarded as a more straightforward alternative to knowledge distillation but also can achieve an effective compromise between expensive computational cost and classification accuracy. In addition, we provide two scene classification schemes of inductive and transductive settings, corresponding to solving the difficulties of remote sensing data acquisition and labeling. The proposed network achieves state-of-the-art results on three benchmark FSRSSC datasets. The potential of the (MESL)-L-2 framework is also demonstrated in combination with classical metalearning-based and metric learning-based few-shot algorithms.
Keyword:
Few-shot learning
global-local contrastive learning
remote sensing scene classification
self-supervised learning
期刊
IF:
8.6
论文数:
2.2W
被引数:
10.7W
机构
引用论文
分享收藏Task-specific contrastive learning for few-shot remote sensing image scene classification任务特定的对比学习在少镜头遥感图像场景分类中的应用
PREAI
分享收藏A cancer pharmacogenomic screen powering crowd-sourced advancement of drug combination prediction.png)
OAAI
IF0
OAAI分享收藏分享收藏Field Verification of Original and Updated National Wetlands Inventory Maps in three Metropolitan Areas in Illinois, USAWetlands
WetlandsIF0
PREAI
分享收藏
查看更多内容